Request URL:https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start=0

Request URL:https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start=20

Request URL:https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start=40

type:movie
tag:热门
sort:recommend
page_limit:20
page_start:0type:movie
tag:热门
sort:recommend
page_limit:20
page_start:20type:movie
tag:热门
sort:recommend
page_limit:20
page_start:40

Host:movie.douban.com
Referer:https://movie.douban.com/explore
User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36
X-Requested-With:XMLHttpRequest

请求地址 = baseurl+type+tag+sort+page_limit+page_startbaseurl：https://movie.douban.com/j/search_subjects?
type:固定为movie
tag:关键字，需要将utf-8转换为urlencode
sort:固定为recommend
page_limit:表示一页显示的电影数量，固定20
page_start:表示电影页数，从0开始，20为公差的递增函数

headers={'Host': 'movie.douban.com','Referer': 'https://movie.douban.com/explore','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36','X-Requested-With': 'XMLHttpRequest'
}

def get_page(page):#请求参数params={'type': 'movie','tag': '奥特曼','sort': 'recommend','page_limit': '20','page_start': page,}#基本网页链接base_url = 'https://movie.douban.com/j/search_subjects?'#将基本网页链接与请求参数结合在一起url = base_url + urlencode(params)try:#获取网页代码resp = requests.get(url, headers=headers)print(url)#返回json数据格式代码if 200 == resp.status_code:print(resp.json())return resp.json()except requests.ConnectionError:return None

def get_image(json):if(json.get('subjects')):data=json.get('subjects')for item in data:title=item.get('title')imageurl=item.get('cover')#返回"信息"字典yield {'title':title,'images':imageurl,}

def save_page(item):#文件夹名称file_name = '奥特曼电影大全'if not os.path.exists(file_name):os.makedirs(file_name)#获取图片链接response=requests.get(item.get('images'))#储存图片文件if response.status_code==200:file_path = file_name + os.path.sep + item.get('title') + '.jpg'with open(file_path, 'wb') as f:f.write(response.content)

def main(page):json = get_page(page)for item in get_image(json):print(item)save_page(item)if __name__ == '__main__':pool = Pool()pool.map(main, [i for i in range(0, 200, 20)])pool.close()pool.join()

import requests
from urllib.parse import urlencode
import os
from multiprocessing.pool import Poolheaders={'Host': 'movie.douban.com','Referer': 'https://movie.douban.com/explore','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36','X-Requested-With': 'XMLHttpRequest'
}def get_page(page):#请求参数params={'type': 'movie','tag': '奥特曼','sort': 'recommend','page_limit': '20','page_start': page,}#基本网页链接base_url = 'https://movie.douban.com/j/search_subjects?'#将基本网页链接与请求参数结合在一起url = base_url + urlencode(params)try:#获取网页代码resp = requests.get(url, headers=headers)print(url)#返回json数据格式代码if 200 == resp.status_code:print(resp.json())return resp.json()except requests.ConnectionError:return Nonedef get_image(json):if(json.get('subjects')):data=json.get('subjects')for item in data:title=item.get('title')imageurl=item.get('cover')#返回"信息"字典yield {'title':title,'images':imageurl,}def save_page(item):#文件夹名称file_name = '奥特曼电影大全'if not os.path.exists(file_name):os.makedirs(file_name)#获取图片链接response=requests.get(item.get('images'))#储存图片文件if response.status_code==200:file_path = file_name + os.path.sep + item.get('title') + '.jpg'with open(file_path, 'wb') as f:f.write(response.content)def main(page):json = get_page(page)for item in get_image(json):print(item)save_page(item)if __name__ == '__main__':pool = Pool()pool.map(main, [i for i in range(0, 200, 20)])pool.close()pool.join()

import requests
from urllib.parse import urlencode
import os
from hashlib import md5
from multiprocessing.pool import Poolheaders={'Host': 'movie.douban.com','Referer': 'https://movie.douban.com/tag/','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
}def get_page(page):params={'sort':'U','range':'0,10','tags':'奥特曼','start': page,}base_url = 'https://movie.douban.com/j/new_search_subjects?'url = base_url + urlencode(params)try:resp = requests.get(url, headers=headers)print(url)if 200 == resp.status_code:print(resp.json())return resp.json()except requests.ConnectionError:return Nonedef get_image(json):if(json.get('data')):data=json.get('data')for item in data:title=item.get('title')imageurl=item.get('cover')yield {'title':title,'images':imageurl,}def save_page(item):file_name='奥特曼大全'+os.path.sep+item.get('title')if not os.path.exists(file_name):os.makedirs(file_name)try:response=requests.get(item.get('images'))if response.status_code==200:file_path = '{0}/{1}.{2}'.format(file_name, md5(response.content).hexdigest(), 'jpg')if not os.path.exists(file_path):with open(file_path, 'wb') as f:f.write(response.content)else:print('Already Downloaded', file_path)except requests.ConnectionError:print('Failed to Save Image')def main(page):json = get_page(page)for item in get_image(json):print(item)save_page(item)if __name__ == '__main__':pool = Pool()pool.map(main, [i for i in range(0, 200, 20)])pool.close()pool.join()